|
--- |
|
license: mit |
|
base_model: microsoft/speecht5_tts |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: zlm_b32_le5_s8000 |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# zlm_b32_le5_s8000 |
|
|
|
This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3854 |
|
|
|
## Model description |
|
|
|
More information needed |
|
|
|
## Intended uses & limitations |
|
|
|
More information needed |
|
|
|
## Training and evaluation data |
|
|
|
More information needed |
|
|
|
## Training procedure |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 1e-05 |
|
- train_batch_size: 32 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 2000 |
|
- training_steps: 8050 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 0.7532 | 0.2094 | 500 | 0.6165 | |
|
| 0.6399 | 0.4188 | 1000 | 0.5227 | |
|
| 0.5333 | 0.6281 | 1500 | 0.4723 | |
|
| 0.5159 | 0.8375 | 2000 | 0.4493 | |
|
| 0.4795 | 1.0469 | 2500 | 0.4283 | |
|
| 0.4821 | 1.2563 | 3000 | 0.4274 | |
|
| 0.4563 | 1.4657 | 3500 | 0.4122 | |
|
| 0.4428 | 1.6750 | 4000 | 0.4040 | |
|
| 0.4604 | 1.8844 | 4500 | 0.4010 | |
|
| 0.4545 | 2.0938 | 5000 | 0.3986 | |
|
| 0.445 | 2.3032 | 5500 | 0.3939 | |
|
| 0.4279 | 2.5126 | 6000 | 0.3892 | |
|
| 0.4451 | 2.7219 | 6500 | 0.3893 | |
|
| 0.4243 | 2.9313 | 7000 | 0.3868 | |
|
| 0.4356 | 3.1407 | 7500 | 0.3857 | |
|
| 0.4429 | 3.3501 | 8000 | 0.3854 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.41.0.dev0 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.19.0 |
|
- Tokenizers 0.19.1 |
|
|
